A mean-field analysis of embedding-space crowding shows a phase transition and Fokker-Planck dynamics that drive retrieval-augmented agents to self-organize toward exclusive service of majority interests.
No free lunch: Retrieval-augmented generation undermines fairness in llms, even for vigilant users.arXiv preprint arXiv:2410.07589,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Introduces FARO, a scalable quadratic optimization approach for fairness-aware top-k retrieval in RAG that mitigates generation bias via controlled reranking and position-aware propagation modeling.
citing papers explorer
-
Fairness-Aware Retrieval Optimization for Retrieval-Augmented Generation
Introduces FARO, a scalable quadratic optimization approach for fairness-aware top-k retrieval in RAG that mitigates generation bias via controlled reranking and position-aware propagation modeling.